Hugging Face's logo

LamaDiab
/
MiniLM-SemanticEngine

Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
dense
Generated from Trainer
dataset_size:169967
loss:MultipleNegativesSymmetricRankingLoss
Eval Results
text-embeddings-inference
Model card Files
xet
Community
LamaDiab commited on
Commit
ac4be89
·
verified ·
1 Parent(s): 9a04d28

Updating model weights

Browse files
Files changed (5) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +440 -0
  3. config_sentence_transformers.json +14 -0
  4. modules.json +20 -0
  5. sentence_bert_config.json +4 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 384,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,440 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0
  <br>features:
1
  <br>modern and attractive design: the doll has a stylish and modern design that suits the tastes of children of different ages.
2
  <br>long and colorful hair: long and colorful hair gives the doll a distinctive and beautiful look, enhancing the possibilities of play and creativity.
3
  <br>wide range of clothes: the game has a large assortment of clothes that allow children to choose the appropriate outfits for the doll character according to their imagination.
4
  <br>multiple accessories: it comes with various accessories that add a touch of distinction and elegance to the doll, allowing to experiment with different styles.
5
  <br>stimulate creativity and imagination: the game helps enhance children's imagination by...</code> | <code>kids</code> |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - dense
7
+ - generated_from_trainer
8
+ - dataset_size:169967
9
+ - loss:MultipleNegativesSymmetricRankingLoss
10
+ base_model: sentence-transformers/all-MiniLM-L6-v2
11
+ widget:
12
+ - source_sentence: blue dianne
13
+ sentences:
14
+ - soap
15
+ - maximize the freshness of your food for 12 hours with the blue dianne thermal
16
+ bag. its triple compartments, spacious storage, heat resistance, and 100% leakproof
17
+ design will keep it fresh. this bpa-free and pvc-free bag is also 100% non-toxic
18
+ and comes with a 3-month guarantee. ideal for everyday food storage.
19
+ - trolley backpack coral high colors 17 l 3 zippers 23977
20
+ - source_sentence: the forty-fifth minute
21
+ sentences:
22
+ - 'literature book '
23
+ - turkish dress.
24
+ - the making of modern middle
25
+ - source_sentence: snowflake pralines & cream
26
+ sentences:
27
+ - smoked turkey sandwich
28
+ - walnut cupcake
29
+ - chicken burrito
30
+ - source_sentence: amytis indigo cushion
31
+ sentences:
32
+ - christian lacroix cushion
33
+ - sealy boats 300 tc cotton bedsheet
34
+ - boys lunch bag
35
+ - source_sentence: hiit biker shorts - black
36
+ sentences:
37
+ - sweet pastry
38
+ - black shorts
39
+ - winter slippers for ladies christmas themed
40
+ pipeline_tag: sentence-similarity
41
+ library_name: sentence-transformers
42
+ metrics:
43
+ - cosine_accuracy
44
+ model-index:
45
+ - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
46
+ results:
47
+ - task:
48
+ type: triplet
49
+ name: Triplet
50
+ dataset:
51
+ name: Unknown
52
+ type: unknown
53
+ metrics:
54
+ - type: cosine_accuracy
55
+ value: 0.9472126364707947
56
+ name: Cosine Accuracy
57
+ ---
58
+
59
+ # SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
60
+
61
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
62
+
63
+ ## Model Details
64
+
65
+ ### Model Description
66
+ - **Model Type:** Sentence Transformer
67
+ - **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
68
+ - **Maximum Sequence Length:** 256 tokens
69
+ - **Output Dimensionality:** 384 dimensions
70
+ - **Similarity Function:** Cosine Similarity
71
+ <!-- - **Training Dataset:** Unknown -->
72
+ <!-- - **Language:** Unknown -->
73
+ <!-- - **License:** Unknown -->
74
+
75
+ ### Model Sources
76
+
77
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
78
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
79
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
80
+
81
+ ### Full Model Architecture
82
+
83
+ ```
84
+ SentenceTransformer(
85
+ (0): Transformer({'max_seq_length': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
86
+ (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
87
+ (2): Normalize()
88
+ )
89
+ ```
90
+
91
+ ## Usage
92
+
93
+ ### Direct Usage (Sentence Transformers)
94
+
95
+ First install the Sentence Transformers library:
96
+
97
+ ```bash
98
+ pip install -U sentence-transformers
99
+ ```
100
+
101
+ Then you can load this model and run inference.
102
+ ```python
103
+ from sentence_transformers import SentenceTransformer
104
+
105
+ # Download from the 🤗 Hub
106
+ model = SentenceTransformer("LamaDiab/MiniLM-SemanticEngine")
107
+ # Run inference
108
+ sentences = [
109
+ 'hiit biker shorts - black',
110
+ 'black shorts',
111
+ 'winter slippers for ladies christmas themed',
112
+ ]
113
+ embeddings = model.encode(sentences)
114
+ print(embeddings.shape)
115
+ # [3, 384]
116
+
117
+ # Get the similarity scores for the embeddings
118
+ similarities = model.similarity(embeddings, embeddings)
119
+ print(similarities)
120
+ # tensor([[ 1.0000, 0.7103, -0.0705],
121
+ # [ 0.7103, 1.0000, -0.0356],
122
+ # [-0.0705, -0.0356, 1.0000]])
123
+ ```
124
+
125
+ <!--
126
+ ### Direct Usage (Transformers)
127
+
128
+ <details><summary>Click to see the direct usage in Transformers</summary>
129
+
130
+ </details>
131
+ -->
132
+
133
+ <!--
134
+ ### Downstream Usage (Sentence Transformers)
135
+
136
+ You can finetune this model on your own dataset.
137
+
138
+ <details><summary>Click to expand</summary>
139
+
140
+ </details>
141
+ -->
142
+
143
+ <!--
144
+ ### Out-of-Scope Use
145
+
146
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
147
+ -->
148
+
149
+ ## Evaluation
150
+
151
+ ### Metrics
152
+
153
+ #### Triplet
154
+
155
+ * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
156
+
157
+ | Metric | Value |
158
+ |:--------------------|:-----------|
159
+ | **cosine_accuracy** | **0.9472** |
160
+
161
+ <!--
162
+ ## Bias, Risks and Limitations
163
+
164
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
165
+ -->
166
+
167
+ <!--
168
+ ### Recommendations
169
+
170
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
171
+ -->
172
+
173
+ ## Training Details
174
+
175
+ ### Training Dataset
176
+
177
+ #### Unnamed Dataset
178
+
179
+ * Size: 169,967 training samples
180
+ * Columns: <code>anchor</code> and <code>positive</code>
181
+ * Approximate statistics based on the first 1000 samples:
182
+ | | anchor | positive |
183
+ |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
184
+ | type | string | string |
185
+ | details | <ul><li>min: 3 tokens</li><li>mean: 8.82 tokens</li><li>max: 237 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 14.99 tokens</li><li>max: 256 tokens</li></ul> |
186
+ * Samples:
187
+ | anchor | positive |
188
+ |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------|
189
+ | <code>orasi barista almond milk is a premium, plant-based milk designed specifically for coffee lovers. crafted to create the perfect froth, it delivers a smooth and creamy texture that enhances the flavor of your lattes, cappuccinos, and other coffee drinks.</code> | <code>groceries</code> |
190
+ | <code>this toy is a "modern fashion" doll, combining beauty and innovation in its design. the doll has long and pink hair that adds a modern and attractive character to it. it comes with a wide variety of clothes and cool accessories that allow children to switch outfits and try different looks.
191
  <br>features:
192
  <br>modern and attractive design: the doll has a stylish and modern design that suits the tastes of children of different ages.
193
  <br>long and colorful hair: long and colorful hair gives the doll a distinctive and beautiful look, enhancing the possibilities of play and creativity.
194
  <br>wide range of clothes: the game has a large assortment of clothes that allow children to choose the appropriate outfits for the doll character according to their imagination.
195
  <br>multiple accessories: it comes with various accessories that add a touch of distinction and elegance to the doll, allowing to experiment with different styles.
196
  <br>stimulate creativity and imagination: the game helps enhance children's imagination by...</code> | <code>kids</code> |
197
+ | <code>zinnia ice box vivid gen.2 - blue</code> | <code>blue ice box</code> |
198
+ * Loss: [<code>MultipleNegativesSymmetricRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativessymmetricrankingloss) with these parameters:
199
+ ```json
200
+ {
201
+ "scale": 20.0,
202
+ "similarity_fct": "cos_sim",
203
+ "gather_across_devices": true
204
+ }
205
+ ```
206
+
207
+ ### Evaluation Dataset
208
+
209
+ #### Unnamed Dataset
210
+
211
+ * Size: 16,216 evaluation samples
212
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
213
+ * Approximate statistics based on the first 1000 samples:
214
+ | | anchor | positive | negative |
215
+ |:--------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
216
+ | type | string | string | string |
217
+ | details | <ul><li>min: 3 tokens</li><li>mean: 9.79 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 19.21 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 9.76 tokens</li><li>max: 67 tokens</li></ul> |
218
+ * Samples:
219
+ | anchor | positive | negative |
220
+ |:--------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------|
221
+ | <code>dosado ring</code> | <code>dosado or dos- à- dos: a wavy movement of two people around eachother, without turning & facing the same direction. material: 18k gold plated hammered brass. size: one size, adjustable. care instructions: to keep the jewelry pieces looking as good as new, please make sure that you store them in an airtight container. they should not come in contact with sweat, water or pefume, alcohol, sanitizers etc. polish with a microfiber cloth.</code> | <code>kiprun ks light men's running shoes - black</code> |
222
+ | <code>puzzle city of fog</code> | <code>this amazing puzzle offers a unique opportunity to explore the beauty of san francisco, also known as the "city by the bay," through assembling a 2000-piece jigsaw. you'll immerse yourself in a world full of colors and details, as your eyes wander across the iconic golden gate bridge, towering buildings, distinctive hilly streets, and sailing ships in the harbor. it’s a panoramic depiction of san francisco, providing a comprehensive view of the city and its landmarks.<br>features:<br>explore san francisco: enjoy a virtual exploration of san francisco without leaving your home. get up close with famous landmarks such as the golden gate bridge and the harbor.<br>improves cognitive skills: assembling the puzzle enhances focus, memory, and fine motor skills while boosting problem-solving and decision-making abilities.<br>relaxation and stress relief: puzzle assembly is a fun and engaging activity that helps to relax and reduce stress, especially when concentrating on the appealing details of san franc...</code> | <code>unicorn</code> |
223
+ | <code>my fault series</code> | <code>mercedes ron book</code> | <code>sophie's world</code> |
224
+ * Loss: [<code>MultipleNegativesSymmetricRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativessymmetricrankingloss) with these parameters:
225
+ ```json
226
+ {
227
+ "scale": 20.0,
228
+ "similarity_fct": "cos_sim",
229
+ "gather_across_devices": true
230
+ }
231
+ ```
232
+
233
+ ### Training Hyperparameters
234
+ #### Non-Default Hyperparameters
235
+
236
+ - `eval_strategy`: steps
237
+ - `per_device_train_batch_size`: 64
238
+ - `per_device_eval_batch_size`: 64
239
+ - `weight_decay`: 0.01
240
+ - `num_train_epochs`: 5
241
+ - `warmup_ratio`: 0.2
242
+ - `fp16`: True
243
+ - `dataloader_num_workers`: 2
244
+ - `dataloader_prefetch_factor`: 2
245
+ - `push_to_hub`: True
246
+ - `hub_model_id`: LamaDiab/MiniLM-SemanticEngine
247
+ - `batch_sampler`: no_duplicates
248
+
249
+ #### All Hyperparameters
250
+ <details><summary>Click to expand</summary>
251
+
252
+ - `overwrite_output_dir`: False
253
+ - `do_predict`: False
254
+ - `eval_strategy`: steps
255
+ - `prediction_loss_only`: True
256
+ - `per_device_train_batch_size`: 64
257
+ - `per_device_eval_batch_size`: 64
258
+ - `per_gpu_train_batch_size`: None
259
+ - `per_gpu_eval_batch_size`: None
260
+ - `gradient_accumulation_steps`: 1
261
+ - `eval_accumulation_steps`: None
262
+ - `torch_empty_cache_steps`: None
263
+ - `learning_rate`: 5e-05
264
+ - `weight_decay`: 0.01
265
+ - `adam_beta1`: 0.9
266
+ - `adam_beta2`: 0.999
267
+ - `adam_epsilon`: 1e-08
268
+ - `max_grad_norm`: 1.0
269
+ - `num_train_epochs`: 5
270
+ - `max_steps`: -1
271
+ - `lr_scheduler_type`: linear
272
+ - `lr_scheduler_kwargs`: {}
273
+ - `warmup_ratio`: 0.2
274
+ - `warmup_steps`: 0
275
+ - `log_level`: passive
276
+ - `log_level_replica`: warning
277
+ - `log_on_each_node`: True
278
+ - `logging_nan_inf_filter`: True
279
+ - `save_safetensors`: True
280
+ - `save_on_each_node`: False
281
+ - `save_only_model`: False
282
+ - `restore_callback_states_from_checkpoint`: False
283
+ - `no_cuda`: False
284
+ - `use_cpu`: False
285
+ - `use_mps_device`: False
286
+ - `seed`: 42
287
+ - `data_seed`: None
288
+ - `jit_mode_eval`: False
289
+ - `use_ipex`: False
290
+ - `bf16`: False
291
+ - `fp16`: True
292
+ - `fp16_opt_level`: O1
293
+ - `half_precision_backend`: auto
294
+ - `bf16_full_eval`: False
295
+ - `fp16_full_eval`: False
296
+ - `tf32`: None
297
+ - `local_rank`: 0
298
+ - `ddp_backend`: None
299
+ - `tpu_num_cores`: None
300
+ - `tpu_metrics_debug`: False
301
+ - `debug`: []
302
+ - `dataloader_drop_last`: False
303
+ - `dataloader_num_workers`: 2
304
+ - `dataloader_prefetch_factor`: 2
305
+ - `past_index`: -1
306
+ - `disable_tqdm`: False
307
+ - `remove_unused_columns`: True
308
+ - `label_names`: None
309
+ - `load_best_model_at_end`: False
310
+ - `ignore_data_skip`: False
311
+ - `fsdp`: []
312
+ - `fsdp_min_num_params`: 0
313
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
314
+ - `fsdp_transformer_layer_cls_to_wrap`: None
315
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
316
+ - `deepspeed`: None
317
+ - `label_smoothing_factor`: 0.0
318
+ - `optim`: adamw_torch
319
+ - `optim_args`: None
320
+ - `adafactor`: False
321
+ - `group_by_length`: False
322
+ - `length_column_name`: length
323
+ - `ddp_find_unused_parameters`: None
324
+ - `ddp_bucket_cap_mb`: None
325
+ - `ddp_broadcast_buffers`: False
326
+ - `dataloader_pin_memory`: True
327
+ - `dataloader_persistent_workers`: False
328
+ - `skip_memory_metrics`: True
329
+ - `use_legacy_prediction_loop`: False
330
+ - `push_to_hub`: True
331
+ - `resume_from_checkpoint`: None
332
+ - `hub_model_id`: LamaDiab/MiniLM-SemanticEngine
333
+ - `hub_strategy`: every_save
334
+ - `hub_private_repo`: None
335
+ - `hub_always_push`: False
336
+ - `hub_revision`: None
337
+ - `gradient_checkpointing`: False
338
+ - `gradient_checkpointing_kwargs`: None
339
+ - `include_inputs_for_metrics`: False
340
+ - `include_for_metrics`: []
341
+ - `eval_do_concat_batches`: True
342
+ - `fp16_backend`: auto
343
+ - `push_to_hub_model_id`: None
344
+ - `push_to_hub_organization`: None
345
+ - `mp_parameters`:
346
+ - `auto_find_batch_size`: False
347
+ - `full_determinism`: False
348
+ - `torchdynamo`: None
349
+ - `ray_scope`: last
350
+ - `ddp_timeout`: 1800
351
+ - `torch_compile`: False
352
+ - `torch_compile_backend`: None
353
+ - `torch_compile_mode`: None
354
+ - `include_tokens_per_second`: False
355
+ - `include_num_input_tokens_seen`: False
356
+ - `neftune_noise_alpha`: None
357
+ - `optim_target_modules`: None
358
+ - `batch_eval_metrics`: False
359
+ - `eval_on_start`: False
360
+ - `use_liger_kernel`: False
361
+ - `liger_kernel_config`: None
362
+ - `eval_use_gather_object`: False
363
+ - `average_tokens_across_devices`: False
364
+ - `prompts`: None
365
+ - `batch_sampler`: no_duplicates
366
+ - `multi_dataset_batch_sampler`: proportional
367
+ - `router_mapping`: {}
368
+ - `learning_rate_mapping`: {}
369
+
370
+ </details>
371
+
372
+ ### Training Logs
373
+ | Epoch | Step | Training Loss | Validation Loss | cosine_accuracy |
374
+ |:------:|:-----:|:-------------:|:---------------:|:---------------:|
375
+ | 0.0004 | 1 | 1.6989 | - | - |
376
+ | 0.1883 | 500 | 1.6103 | 1.4441 | 0.9124 |
377
+ | 0.3765 | 1000 | 1.1942 | 1.3155 | 0.9233 |
378
+ | 0.5648 | 1500 | 0.9831 | 1.2584 | 0.9257 |
379
+ | 0.7530 | 2000 | 0.8867 | 1.2368 | 0.9254 |
380
+ | 0.9413 | 2500 | 0.8094 | 1.1874 | 0.9274 |
381
+ | 1.1295 | 3000 | 0.5818 | 1.1431 | 0.9348 |
382
+ | 1.3178 | 3500 | 0.6978 | 1.1291 | 0.9374 |
383
+ | 1.5060 | 4000 | 0.6652 | 1.0936 | 0.9389 |
384
+ | 1.6943 | 4500 | 0.6287 | 1.0889 | 0.9369 |
385
+ | 1.8825 | 5000 | 0.5986 | 1.0780 | 0.9404 |
386
+ | 2.0708 | 5500 | 0.4376 | 1.0783 | 0.9386 |
387
+ | 2.2590 | 6000 | 0.511 | 1.0674 | 0.9405 |
388
+ | 2.4473 | 6500 | 0.4997 | 1.0412 | 0.9427 |
389
+ | 2.6355 | 7000 | 0.4985 | 1.0160 | 0.9441 |
390
+ | 2.8238 | 7500 | 0.4798 | 1.0264 | 0.9434 |
391
+ | 3.0120 | 8000 | 0.3477 | 1.0153 | 0.9455 |
392
+ | 3.2003 | 8500 | 0.4117 | 1.0177 | 0.9461 |
393
+ | 3.3886 | 9000 | 0.4302 | 1.0071 | 0.9451 |
394
+ | 3.5768 | 9500 | 0.4046 | 1.0171 | 0.9460 |
395
+ | 3.7651 | 10000 | 0.414 | 0.9819 | 0.9474 |
396
+ | 3.9533 | 10500 | 0.3786 | 0.9982 | 0.9463 |
397
+ | 4.1416 | 11000 | 0.2952 | 0.9920 | 0.9461 |
398
+ | 4.3298 | 11500 | 0.3655 | 0.9959 | 0.9455 |
399
+ | 4.5181 | 12000 | 0.3655 | 0.9961 | 0.9464 |
400
+ | 4.7063 | 12500 | 0.3662 | 0.9826 | 0.9467 |
401
+ | 4.8946 | 13000 | 0.3545 | 0.9864 | 0.9472 |
402
+
403
+
404
+ ### Framework Versions
405
+ - Python: 3.11.13
406
+ - Sentence Transformers: 5.1.2
407
+ - Transformers: 4.53.3
408
+ - PyTorch: 2.6.0+cu124
409
+ - Accelerate: 1.9.0
410
+ - Datasets: 4.4.1
411
+ - Tokenizers: 0.21.2
412
+
413
+ ## Citation
414
+
415
+ ### BibTeX
416
+
417
+ #### Sentence Transformers
418
+ ```bibtex
419
+ @inproceedings{reimers-2019-sentence-bert,
420
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
421
+ author = "Reimers, Nils and Gurevych, Iryna",
422
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
423
+ month = "11",
424
+ year = "2019",
425
+ publisher = "Association for Computational Linguistics",
426
+ url = "https://arxiv.org/abs/1908.10084",
427
+ }
428
+ ```
429
+
430
+ <!--
431
+ ## Glossary
432
+
433
+ *Clearly define terms in order to be accessible across audiences.*
434
+ -->
435
+
436
+ <!--
437
+ ## Model Card Authors
438
+
439
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
440
+ -->
441
+
442
+ <!--
443
+ ## Model Card Contact
444
+
445
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
446
+ -->
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "5.1.2",
4
+ "transformers": "4.53.3",
5
+ "pytorch": "2.6.0+cu124"
6
+ },
7
+ "model_type": "SentenceTransformer",
8
+ "prompts": {
9
+ "query": "",
10
+ "document": ""
11
+ },
12
+ "default_prompt_name": null,
13
+ "similarity_fn_name": "cosine"
14
+ }
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 256,
3
+ "do_lower_case": false
4
+ }